m1une's library

This documentation is automatically generated by online-judge-tools/verification-helper

View on GitHub

:heavy_check_mark: verify/string/aho_corasick.test.cpp

Depends on

Code

#define PROBLEM "https://judge.yosupo.jp/problem/aho_corasick"

#include "../../string/aho_corasick.hpp"

#include <algorithm>
#include <cassert>
#include <cstdint>
#include "../../utilities/fast_io.hpp"
#include <string>
#include <tuple>
#include <vector>

namespace {

void check(
    const std::vector<std::string>& patterns,
    const std::string& text
) {
    m1une::string::AhoCorasick<4, 'a'> automaton;
    std::size_t total_length = 1;
    for (const std::string& pattern : patterns) {
        total_length += pattern.size();
    }
    automaton.reserve(total_length);
    for (int id = 0; id < int(patterns.size()); ++id) {
        assert(automaton.insert(patterns[id]) == id);
        assert(automaton.pattern_length(id) == int(patterns[id].size()));
    }
    automaton.build();
    assert(automaton.built());
    assert(automaton.pattern_count() == int(patterns.size()));
    assert(automaton.nodes().size() == automaton.node_count());
    assert(automaton.bfs_order().size() == automaton.node_count());
    assert(automaton.bfs_order().front() == automaton.root());

    std::vector<int> failure_parent_count(automaton.node_count(), 0);
    for (const auto& node : automaton.nodes()) {
        for (int child : node.failure_children) {
            failure_parent_count[child]++;
        }
    }
    for (int node = 1; node < int(automaton.node_count()); ++node) {
        assert(failure_parent_count[node] == 1);
        assert(
            automaton.node(automaton.node(node).failure).depth
            < automaton.node(node).depth
        );
        assert(
            std::find(
                automaton.node(automaton.node(node).parent).children.begin(),
                automaton.node(automaton.node(node).parent).children.end(),
                node
            ) != automaton.node(automaton.node(node).parent).children.end()
        );
        assert(
            automaton.node(automaton.node(node).parent)
                .next[automaton.node(node).parent_symbol]
            == node
        );
    }
    for (int id = 0; id < int(patterns.size()); ++id) {
        [[maybe_unused]] int terminal = automaton.pattern_node(id);
        assert(automaton.node(terminal).depth == int(patterns[id].size()));
        assert(
            std::find(
                automaton.node(terminal).pattern_ids.begin(),
                automaton.node(terminal).pattern_ids.end(),
                id
            ) != automaton.node(terminal).pattern_ids.end()
        );
    }

    std::vector<std::tuple<int, int>> actual;
    automaton.match(text, [&actual](int end, int pattern_id) {
        actual.emplace_back(end, pattern_id);
    });
    std::sort(actual.begin(), actual.end());

    std::vector<std::tuple<int, int>> expected;
    std::vector<long long> expected_count(patterns.size(), 0);
    for (int end = 0; end <= int(text.size()); ++end) {
        for (int id = 0; id < int(patterns.size()); ++id) {
            int length = int(patterns[id].size());
            if (
                length <= end &&
                text.compare(end - length, length, patterns[id]) == 0
            ) {
                expected.emplace_back(end, id);
                expected_count[id]++;
            }
        }
    }
    std::sort(expected.begin(), expected.end());
    assert(actual == expected);
    assert(automaton.count_occurrences(text) == expected_count);
}

void test_fixed() {
    check({}, "abacaba");
    check({""}, "");
    check({"", "", "a", "a", "aa", "ba"}, "aaaaba");

    m1une::string::AhoCorasick<10, '0'> digits;
    [[maybe_unused]] int first = digits.insert(std::string("12"));
    [[maybe_unused]] int second = digits.insert(std::string("2"));
    digits.build();
    auto count = digits.count_occurrences(std::string("1212"));
    assert(count[first] == 2);
    assert(count[second] == 2);

    digits.clear();
    assert(!digits.built());
    assert(digits.pattern_count() == 0);
    assert(digits.node_count() == 1);
}

void test_randomized() {
    std::uint64_t state = 313;
    auto random = [&state]() {
        state ^= state << 7;
        state ^= state >> 9;
        return state;
    };

    for (int trial = 0; trial < 4000; ++trial) {
        int pattern_count = int(random() % 15);
        std::vector<std::string> patterns;
        for (int id = 0; id < pattern_count; ++id) {
            int length = int(random() % 8);
            std::string pattern(length, 'a');
            for (char& symbol : pattern) {
                symbol = char('a' + random() % 4);
            }
            patterns.push_back(std::move(pattern));
        }

        int text_length = int(random() % 35);
        std::string text(text_length, 'a');
        for (char& symbol : text) {
            symbol = char('a' + random() % 4);
        }
        check(patterns, text);
    }
}

}  // namespace

int main() {
    m1une::utilities::FastInput fast_input;
    m1une::utilities::FastOutput fast_output;

    test_fixed();
    test_randomized();
    int n;
    fast_input >> n;
    m1une::string::AhoCorasick<> automaton;
    for (int i = 0; i < n; i++) {
        std::string pattern;
        fast_input >> pattern;
        automaton.insert(pattern);
    }
    automaton.build();

    int node_count = int(automaton.node_count());
    fast_output << node_count << '\n';
    for (int id = 1; id < node_count; id++) {
        const auto& node = automaton.node(id);
        fast_output << node.parent << ' ' << node.failure << '\n';
    }
    for (int i = 0; i < n; i++) {
        if (i) fast_output << ' ';
        fast_output << automaton.pattern_node(i);
    }
    fast_output << '\n';
}
#line 1 "verify/string/aho_corasick.test.cpp"
#define PROBLEM "https://judge.yosupo.jp/problem/aho_corasick"

#line 1 "string/aho_corasick.hpp"



#include <array>
#include <cassert>
#include <cstddef>
#include <limits>
#include <queue>
#include <vector>

namespace m1une {
namespace string {

// Aho-Corasick automaton for a contiguous character alphabet.
template <int AlphabetSize = 26, int FirstCharacter = 'a'>
struct AhoCorasick {
    static_assert(0 < AlphabetSize);

    using node_id = int;
    static constexpr node_id null_node = -1;

    struct Node {
        // Completed automaton transitions. Valid after build().
        std::array<node_id, AlphabetSize> next;
        node_id failure;
        node_id output_link;
        node_id parent;
        int parent_symbol;
        int depth;
        std::vector<node_id> children;
        std::vector<node_id> failure_children;
        std::vector<int> pattern_ids;

        Node(
            node_id parent_value = null_node,
            int parent_symbol_value = -1,
            int depth_value = 0
        ) : failure(0),
            output_link(null_node),
            parent(parent_value),
            parent_symbol(parent_symbol_value),
            depth(depth_value) {
            next.fill(null_node);
        }
    };

   private:
    std::vector<Node> _nodes;
    std::vector<int> _pattern_length;
    std::vector<node_id> _pattern_node;
    std::vector<node_id> _bfs_order;
    bool _built;

    template <class Symbol>
    static int symbol_index(const Symbol& symbol) {
        int index = int(symbol) - FirstCharacter;
        assert(0 <= index && index < AlphabetSize);
        return index;
    }

    node_id new_node(node_id parent, int parent_symbol) {
        assert(_nodes.size() < std::size_t(std::numeric_limits<int>::max()));
        assert(_nodes[parent].depth < std::numeric_limits<int>::max());
        _nodes.emplace_back(parent, parent_symbol, _nodes[parent].depth + 1);
        return int(_nodes.size()) - 1;
    }

   public:
    AhoCorasick() : _nodes(1), _built(false) {}

    node_id root() const {
        return 0;
    }

    bool built() const {
        return _built;
    }

    int pattern_count() const {
        return int(_pattern_length.size());
    }

    int pattern_length(int pattern_id) const {
        assert(0 <= pattern_id && pattern_id < pattern_count());
        return _pattern_length[pattern_id];
    }

    node_id pattern_node(int pattern_id) const {
        assert(0 <= pattern_id && pattern_id < pattern_count());
        return _pattern_node[pattern_id];
    }

    std::size_t node_count() const {
        return _nodes.size();
    }

    const std::vector<Node>& nodes() const {
        return _nodes;
    }

    const Node& node(node_id id) const {
        assert(0 <= id && std::size_t(id) < _nodes.size());
        return _nodes[id];
    }

    // Returns nodes in failure-link BFS order, beginning with the root.
    const std::vector<node_id>& bfs_order() const {
        assert(_built);
        return _bfs_order;
    }

    void reserve(std::size_t node_capacity) {
        assert(!_built);
        _nodes.reserve(node_capacity);
    }

    void clear() {
        _nodes.clear();
        _nodes.emplace_back();
        _pattern_length.clear();
        _pattern_node.clear();
        _bfs_order.clear();
        _built = false;
    }

    // Inserts a pattern and returns its insertion-order ID.
    template <class Sequence>
    int insert(const Sequence& pattern) {
        assert(!_built);
        int pattern_id = pattern_count();
        int length = 0;
        node_id state = root();
        for (const auto& symbol : pattern) {
            assert(length < std::numeric_limits<int>::max());
            int index = symbol_index(symbol);
            if (_nodes[state].next[index] == null_node) {
                node_id child = new_node(state, index);
                _nodes[state].next[index] = child;
                _nodes[state].children.push_back(child);
            }
            state = _nodes[state].next[index];
            length++;
        }
        _nodes[state].pattern_ids.push_back(pattern_id);
        _pattern_length.push_back(length);
        _pattern_node.push_back(state);
        return pattern_id;
    }

    // Builds failure links and completes every automaton transition.
    void build() {
        assert(!_built);
        std::queue<node_id> queue;
        _bfs_order.clear();
        _bfs_order.reserve(_nodes.size());
        _bfs_order.push_back(root());

        for (int symbol = 0; symbol < AlphabetSize; ++symbol) {
            node_id child = _nodes[root()].next[symbol];
            if (child == null_node) {
                _nodes[root()].next[symbol] = root();
            } else {
                _nodes[root()].next[symbol] = child;
                _nodes[child].failure = root();
                _nodes[child].output_link =
                    _nodes[root()].pattern_ids.empty() ? null_node : root();
                _nodes[root()].failure_children.push_back(child);
                queue.push(child);
            }
        }

        while (!queue.empty()) {
            node_id state = queue.front();
            queue.pop();
            _bfs_order.push_back(state);

            for (int symbol = 0; symbol < AlphabetSize; ++symbol) {
                node_id child = _nodes[state].next[symbol];
                if (child == null_node) {
                    _nodes[state].next[symbol] =
                        _nodes[_nodes[state].failure].next[symbol];
                    continue;
                }

                _nodes[state].next[symbol] = child;
                node_id failure =
                    _nodes[_nodes[state].failure].next[symbol];
                _nodes[child].failure = failure;
                _nodes[child].output_link =
                    _nodes[failure].pattern_ids.empty()
                        ? _nodes[failure].output_link
                        : failure;
                _nodes[failure].failure_children.push_back(child);
                queue.push(child);
            }
        }
        _built = true;
    }

    template <class Symbol>
    node_id transition(node_id state, const Symbol& symbol) const {
        assert(_built);
        assert(0 <= state && std::size_t(state) < _nodes.size());
        return _nodes[state].next[symbol_index(symbol)];
    }

    // Calls callback(pattern_id) for every pattern ending at `state`.
    template <class Callback>
    void for_each_output(node_id state, Callback callback) const {
        assert(_built);
        assert(0 <= state && std::size_t(state) < _nodes.size());
        while (state != null_node) {
            for (int pattern_id : _nodes[state].pattern_ids) {
                callback(pattern_id);
            }
            state = _nodes[state].output_link;
        }
    }

    // Calls callback(end, pattern_id) for every occurrence. `end` is the
    // exclusive end position. Empty patterns occur at every text boundary.
    template <class Sequence, class Callback>
    void match(const Sequence& text, Callback callback) const {
        assert(_built);
        node_id state = root();
        for_each_output(state, [&callback](int pattern_id) {
            callback(0, pattern_id);
        });

        int end = 0;
        for (const auto& symbol : text) {
            state = transition(state, symbol);
            end++;
            for_each_output(state, [&callback, end](int pattern_id) {
                callback(end, pattern_id);
            });
        }
    }

    // Counts occurrences of every inserted pattern in linear time.
    template <class Sequence>
    std::vector<long long> count_occurrences(const Sequence& text) const {
        assert(_built);
        std::vector<long long> visits(_nodes.size(), 0);
        node_id state = root();
        visits[root()]++;
        for (const auto& symbol : text) {
            state = transition(state, symbol);
            visits[state]++;
        }

        for (std::size_t index = _bfs_order.size(); index-- > 1;) {
            node_id current = _bfs_order[index];
            visits[_nodes[current].failure] += visits[current];
        }

        std::vector<long long> result(pattern_count(), 0);
        for (node_id current : _bfs_order) {
            for (int pattern_id : _nodes[current].pattern_ids) {
                result[pattern_id] = visits[current];
            }
        }
        return result;
    }
};

}  // namespace string
}  // namespace m1une


#line 4 "verify/string/aho_corasick.test.cpp"

#include <algorithm>
#line 7 "verify/string/aho_corasick.test.cpp"
#include <cstdint>
#line 1 "utilities/fast_io.hpp"



#line 6 "utilities/fast_io.hpp"
#include <cerrno>
#include <charconv>
#line 9 "utilities/fast_io.hpp"
#include <cstdio>
#include <cstdlib>
#line 12 "utilities/fast_io.hpp"
#include <cstring>
#include <iterator>
#include <string>
#include <sys/stat.h>
#include <type_traits>
#include <utility>
#include <unistd.h>
#line 20 "utilities/fast_io.hpp"

namespace m1une {
namespace utilities {

struct FastOutput;

namespace internal {

// Shared with the convenience helpers in template.hpp.
inline FastOutput* standard_output_instance = nullptr;

// Detect std::begin(x), std::end(x).
template <class T, class = void>
struct is_range : std::false_type {};

template <class T>
struct is_range<T, std::void_t<
    decltype(std::begin(std::declval<T&>())),
    decltype(std::end(std::declval<T&>()))
>> : std::true_type {};

template <class T>
inline constexpr bool is_range_v = is_range<T>::value;

template <class T>
using range_reference_t = decltype(*std::begin(std::declval<T&>()));

template <class T>
using range_value_t = std::remove_cv_t<std::remove_reference_t<range_reference_t<T>>>;

template <class T, class = void>
struct range_stored_value {
    using type = range_value_t<T>;
};

template <class T>
struct range_stored_value<T, std::void_t<typename std::remove_cv_t<std::remove_reference_t<T>>::value_type>> {
    using type = typename std::remove_cv_t<std::remove_reference_t<T>>::value_type;
};

template <class T>
using range_stored_value_t = typename range_stored_value<T>::type;

// Treat strings and C strings as scalar output objects, not as ranges.
template <class T>
struct is_char_array : std::false_type {};

template <class T, std::size_t N>
struct is_char_array<T[N]>
    : std::bool_constant<std::is_same_v<std::remove_cv_t<T>, char>> {};

template <class T>
struct is_string_like
    : std::bool_constant<
          std::is_same_v<std::decay_t<T>, std::string>
          || std::is_same_v<std::decay_t<T>, const char*>
          || std::is_same_v<std::decay_t<T>, char*>
          || is_char_array<std::remove_reference_t<T>>::value
      > {};

template <class T>
inline constexpr bool is_string_like_v = is_string_like<T>::value;

// ModInt-like type: x.val() is printable, and x can be assigned from long long.
template <class T, class = void>
struct has_val_method : std::false_type {};

template <class T>
struct has_val_method<T, std::void_t<decltype(std::declval<const T&>().val())>>
    : std::true_type {};

template <class T>
inline constexpr bool has_val_method_v = has_val_method<T>::value;

template <class T, class = void>
struct has_static_mod_raw : std::false_type {};

template <class T>
struct has_static_mod_raw<
    T, std::void_t<decltype(T::mod()), decltype(T::raw(std::declval<uint32_t>()))>>
    : std::true_type {};

template <class T>
inline constexpr bool has_static_mod_raw_v = has_static_mod_raw<T>::value;

// libstdc++ before GCC 16 does not classify __int128 as an integral type in
// strict ISO modes such as -std=c++23. Keep the fast-I/O interface independent
// of that implementation detail.
template <class T>
inline constexpr bool is_integral_v =
    std::is_integral_v<T>
    || std::is_same_v<std::remove_cv_t<T>, __int128_t>
    || std::is_same_v<std::remove_cv_t<T>, __uint128_t>;

template <class T>
inline constexpr bool is_signed_v =
    std::is_signed_v<T>
    || std::is_same_v<std::remove_cv_t<T>, __int128_t>;

template <class T>
struct make_unsigned {
    using type = std::make_unsigned_t<T>;
};

template <>
struct make_unsigned<__int128_t> {
    using type = __uint128_t;
};

template <>
struct make_unsigned<__uint128_t> {
    using type = __uint128_t;
};

template <class T>
using make_unsigned_t = typename make_unsigned<std::remove_cv_t<T>>::type;

}  // namespace internal

struct FastInput {
    static constexpr int buffer_size = 1 << 20;

   private:
    std::FILE* _stream;
    char _buffer[buffer_size];
    int _position;
    int _length;
    int _file_descriptor;
    bool _streaming;

    bool refill() {
        _position = 0;
        if (_streaming) {
            ssize_t length;
            do {
                length = ::read(_file_descriptor, _buffer, buffer_size);
            } while (length < 0 && errno == EINTR);
            if (length <= 0) {
                _length = 0;
                return false;
            }
            _length = int(length);
        } else {
            _length = int(std::fread(_buffer, 1, buffer_size, _stream));
        }
        return _length != 0;
    }

    template <class T>
    bool read_integer_from_stream(T& value) {
        if (!skip_spaces()) return false;
        int c = read_char_raw();

        bool negative = false;
        if (c == '-') {
            negative = true;
            c = read_char_raw();
        }

        if constexpr (internal::is_signed_v<T>) {
            T result = 0;
            while ('0' <= c && c <= '9') {
                result = negative ? result * 10 - (c - '0')
                                  : result * 10 + (c - '0');
                c = read_char_raw();
            }
            value = result;
        } else {
            T result = 0;
            while ('0' <= c && c <= '9') {
                result = result * 10 + T(c - '0');
                c = read_char_raw();
            }
            value = negative ? T(0) - result : result;
        }
        return true;
    }

    bool prepare_number() {
        if (_length - _position >= 64) return true;
        const int remaining = _length - _position;
        if (remaining > 0) std::memmove(_buffer, _buffer + _position, remaining);
        const int added = int(std::fread(_buffer + remaining, 1, buffer_size - remaining, _stream));
        _position = 0;
        _length = remaining + added;
        if (_length < buffer_size) _buffer[_length] = '\0';
        return _length != 0;
    }

   public:
    explicit FastInput(std::FILE* stream = stdin)
        : _stream(stream),
          _position(0),
          _length(0),
          _file_descriptor(::fileno(stream)),
          _streaming([&] {
              struct stat status;
              return _file_descriptor >= 0
                     && ::fstat(_file_descriptor, &status) == 0
                     && !S_ISREG(status.st_mode);
          }()) {}

    FastInput(const FastInput&) = delete;
    FastInput& operator=(const FastInput&) = delete;

    int read_char_raw() {
        if (_position == _length && !refill()) return EOF;
        return _buffer[_position++];
    }

    bool skip_spaces() {
        int c = read_char_raw();
        while (c != EOF && c <= ' ') c = read_char_raw();
        if (c == EOF) return false;
        --_position;
        return true;
    }

    bool read(char& value) {
        if (!skip_spaces()) return false;
        value = char(read_char_raw());
        return true;
    }

    bool read(std::string& value) {
        if (!skip_spaces()) return false;
        value.clear();
        while (true) {
            const int begin = _position;
            while (_position < _length &&
                   static_cast<unsigned char>(_buffer[_position]) > ' ') {
                ++_position;
            }
            value.append(_buffer + begin, _position - begin);
            if (_position < _length) {
                ++_position;
                return true;
            }
            if (!refill()) return true;
        }
    }

    bool read(bool& value) {
        int x;
        if (!read(x)) return false;
        value = x != 0;
        return true;
    }

    template <class T>
    std::enable_if_t<
        internal::is_integral_v<T>
            && !std::is_same_v<std::remove_cv_t<T>, bool>
            && !std::is_same_v<std::remove_cv_t<T>, char>,
        bool
    >
    read(T& value) {
        if (_streaming) return read_integer_from_stream(value);
        if (!prepare_number()) return false;
        int c = static_cast<unsigned char>(_buffer[_position++]);
        while (c <= ' ') c = static_cast<unsigned char>(_buffer[_position++]);

        bool negative = false;
        if (c == '-') {
            negative = true;
            c = static_cast<unsigned char>(_buffer[_position++]);
        }

        if constexpr (internal::is_signed_v<T>) {
            T result = 0;
            while ('0' <= c && c <= '9') {
                const int first = c - '0';
                const int second = static_cast<unsigned char>(_buffer[_position]) - '0';
                if (0 <= second && second <= 9) {
                    result = negative ? result * 100 - (first * 10 + second)
                                      : result * 100 + (first * 10 + second);
                    ++_position;
                } else {
                    result = negative ? result * 10 - first : result * 10 + first;
                }
                c = static_cast<unsigned char>(_buffer[_position++]);
            }
            value = result;
        } else {
            T result = 0;
            while ('0' <= c && c <= '9') {
                const unsigned first = unsigned(c - '0');
                const int second = static_cast<unsigned char>(_buffer[_position]) - '0';
                if (0 <= second && second <= 9) {
                    result = result * 100 + T(first * 10 + unsigned(second));
                    ++_position;
                } else {
                    result = result * 10 + T(first);
                }
                c = static_cast<unsigned char>(_buffer[_position++]);
            }
            value = negative ? T(0) - result : result;
        }
        if (_position > _length) _position = _length;
        return true;
    }

    template <class T>
    std::enable_if_t<std::is_floating_point_v<T>, bool>
    read(T& value) {
        if (!skip_spaces()) return false;
        int c = read_char_raw();
        bool negative = false;
        if (c == '-' || c == '+') {
            negative = c == '-';
            c = read_char_raw();
        }

        long double result = 0;
        while ('0' <= c && c <= '9') {
            result = result * 10 + (c - '0');
            c = read_char_raw();
        }
        if (c == '.') {
            long double place = 0.1L;
            c = read_char_raw();
            while ('0' <= c && c <= '9') {
                result += (c - '0') * place;
                place *= 0.1L;
                c = read_char_raw();
            }
        }
        if (c == 'e' || c == 'E') {
            c = read_char_raw();
            bool exponent_negative = false;
            if (c == '-' || c == '+') {
                exponent_negative = c == '-';
                c = read_char_raw();
            }
            int exponent = 0;
            while ('0' <= c && c <= '9') {
                exponent = exponent * 10 + (c - '0');
                c = read_char_raw();
            }
            long double scale = 1;
            long double power = 10;
            while (exponent > 0) {
                if (exponent & 1) scale *= power;
                power *= power;
                exponent >>= 1;
            }
            result = exponent_negative ? result / scale : result * scale;
        }
        value = static_cast<T>(negative ? -result : result);
        return true;
    }

    template <class T>
    std::enable_if_t<
        internal::has_val_method_v<T>
            && !internal::is_integral_v<T>
            && !internal::is_range_v<T>,
        bool
    >
    read(T& value) {
        long long x;
        if (!read(x)) return false;
        if constexpr (internal::has_static_mod_raw_v<T>) {
            if (x >= 0 && uint64_t(x) < uint64_t(T::mod())) {
                value = T::raw(uint32_t(x));
            } else {
                value = T(x);
            }
        } else {
            value = T(x);
        }
        return true;
    }

    template <class First, class Second>
    bool read(std::pair<First, Second>& value) {
        if (!read(value.first)) return false;
        return read(value.second);
    }

    template <class Range>
    std::enable_if_t<
        internal::is_range_v<Range>
            && !internal::is_string_like_v<Range>,
        bool
    >
    read(Range& range) {
        using StoredValue = internal::range_stored_value_t<Range>;
        constexpr bool nested = internal::is_range_v<StoredValue>
                                && !internal::is_string_like_v<StoredValue>;

        for (auto&& value : range) {
            if constexpr (std::is_same_v<StoredValue, bool> && !nested) {
                bool x;
                if (!read(x)) return false;
                value = x;
            } else {
                if (!read(value)) return false;
            }
        }
        return true;
    }

    template <class First, class Second, class... Rest>
    bool read(First& first, Second& second, Rest&... rest) {
        if (!read(first)) return false;
        return read(second, rest...);
    }

    template <class T>
    FastInput& operator>>(T& value) {
        if (!read(value)) std::abort();
        return *this;
    }
};

struct FastOutput {
    static constexpr int buffer_size = 1 << 20;

   private:
    inline static const auto digit_quads = [] {
        std::array<char, 40000> result{};
        for (int i = 0; i < 10000; i++) {
            int value = i;
            for (int j = 3; j >= 0; j--) {
                result[4 * i + j] = char('0' + value % 10);
                value /= 10;
            }
        }
        return result;
    }();

    std::FILE* _stream;
    char _buffer[buffer_size];
    int _position;
    int _precision;
    std::chars_format _float_format;
    char _range_separator;
    std::string* _capture = nullptr;

    template <class T>
    std::string format_cell(const T& value) {
        std::string result;
        struct CaptureGuard {
            std::string*& target;
            std::string* previous;
            ~CaptureGuard() { target = previous; }
        } guard{_capture, _capture};
        _capture = &result;
        write(value);
        return result;
    }

    template <class Matrix>
    void write_aligned_matrix(const Matrix& matrix) {
        std::vector<std::vector<std::string>> rows;
        std::vector<std::size_t> widths;
        for (const auto& row : matrix) {
            auto& cells = rows.emplace_back();
            std::size_t column = 0;
            for (const auto& value : row) {
                cells.push_back(format_cell(value));
                if (column == widths.size()) widths.push_back(0);
                widths[column] = std::max(widths[column], cells.back().size());
                ++column;
            }
        }
        bool first = true;
        for (const auto& row : rows) {
            if (!first) write_char('\n');
            first = false;
            for (std::size_t column = 0; column < row.size(); ++column) {
                if (column != 0) write_char(_range_separator);
                for (std::size_t padding = row[column].size();
                     padding < widths[column]; ++padding) {
                    write_char(' ');
                }
                write(row[column]);
            }
        }
    }

   public:
    explicit FastOutput(std::FILE* stream = stdout)
        : _stream(stream),
          _position(0),
          _precision(6),
          _float_format(std::chars_format::general),
          _range_separator(' ') {
        if (_stream == stdout
            && internal::standard_output_instance == nullptr) {
            internal::standard_output_instance = this;
        }
    }

    FastOutput(const FastOutput&) = delete;
    FastOutput& operator=(const FastOutput&) = delete;

    ~FastOutput() {
        flush();
        if (internal::standard_output_instance == this) {
            internal::standard_output_instance = nullptr;
        }
    }

    void flush() {
        if (_position != 0) {
            std::fwrite(_buffer, 1, _position, _stream);
            _position = 0;
        }
        std::fflush(_stream);
    }

    void write_char(char c) {
        if (_capture != nullptr) {
            _capture->push_back(c);
            return;
        }
        if (_position == buffer_size) flush();
        _buffer[_position++] = c;
    }

    void write(const char* s) {
        while (*s != '\0') write_char(*s++);
    }

    void write(const std::string& s) {
        if (_capture != nullptr) {
            _capture->append(s);
            return;
        }
        std::size_t position = 0;
        while (position < s.size()) {
            if (_position == buffer_size) flush();
            const std::size_t copied =
                std::min<std::size_t>(buffer_size - _position, s.size() - position);
            std::memcpy(_buffer + _position, s.data() + position, copied);
            _position += int(copied);
            position += copied;
        }
    }

    void write(char c) {
        write_char(c);
    }

    void write(bool value) {
        write_char(value ? '1' : '0');
    }

    template <class T>
    std::enable_if_t<std::is_floating_point_v<T>>
    write(T value) {
        char digits[128];
        auto [end, error] = std::to_chars(
            digits,
            digits + sizeof(digits),
            value,
            _float_format,
            _precision
        );
        if (error != std::errc()) std::abort();
        for (const char* pointer = digits; pointer != end; pointer++) {
            write_char(*pointer);
        }
    }

    template <class T>
    std::enable_if_t<
        internal::is_integral_v<T>
            && !std::is_same_v<std::remove_cv_t<T>, bool>
            && !std::is_same_v<std::remove_cv_t<T>, char>
    >
    write(T value) {
        using Raw = std::remove_cv_t<T>;
        using Unsigned = internal::make_unsigned_t<Raw>;

        Unsigned magnitude;
        if constexpr (internal::is_signed_v<Raw>) {
            if (value < 0) {
                write_char('-');
                magnitude = Unsigned(0) - Unsigned(value);
            } else {
                magnitude = Unsigned(value);
            }
        } else {
            magnitude = value;
        }

        if (magnitude == 0) {
            write_char('0');
            return;
        }

        unsigned chunks[16];
        int count = 0;
        while (magnitude >= 10000) {
            const Unsigned quotient = magnitude / 10000;
            chunks[count++] = unsigned(magnitude - quotient * 10000);
            magnitude = quotient;
        }
        if (_capture == nullptr && _position > buffer_size - 64) flush();
        char captured[64];
        char* const begin = _capture != nullptr ? captured : _buffer + _position;
        char* destination = begin;
        const unsigned leading = unsigned(magnitude);
        const char* first = digit_quads.data() + 4 * leading;
        int skip = leading < 10 ? 3 : leading < 100 ? 2 : leading < 1000 ? 1 : 0;
        for (; skip < 4; skip++) *destination++ = first[skip];
        while (count--) {
            const char* digits = digit_quads.data() + 4 * chunks[count];
            std::memcpy(destination, digits, 4);
            destination += 4;
        }
        if (_capture != nullptr) {
            _capture->append(begin, destination - begin);
        } else {
            _position += int(destination - begin);
        }
    }

    template <class T>
    std::enable_if_t<
        internal::has_val_method_v<T>
            && !internal::is_integral_v<T>
            && !internal::is_range_v<T>
    >
    write(const T& value) {
        write(value.val());
    }

    template <class First, class Second>
    void write(const std::pair<First, Second>& value) {
        write(value.first);
        write_char(' ');
        write(value.second);
    }

    template <class Range>
    std::enable_if_t<
        internal::is_range_v<Range>
            && !internal::is_string_like_v<Range>
    >
    write(const Range& range) {
        using StoredValue = internal::range_stored_value_t<const Range>;
        constexpr bool nested = internal::is_range_v<StoredValue>
                                && !internal::is_string_like_v<StoredValue>;

        bool first = true;
        for (const auto& value : range) {
            if (!first) write_char(nested ? '\n' : _range_separator);
            first = false;
            if constexpr (std::is_same_v<StoredValue, bool> && !nested) {
                write(static_cast<bool>(value));
            } else {
                write(value);
            }
        }
    }

    template <class First, class... Rest>
    void print(const First& first, const Rest&... rest) {
        write(first);
        ((write_char(' '), write(rest)), ...);
    }

    void println() {
        write_char('\n');
    }

    void set_precision(int precision) {
        _precision = precision;
    }

    void set_fixed(int precision = 6) {
        _float_format = std::chars_format::fixed;
        _precision = precision;
    }

    void set_general(int precision = 6) {
        _float_format = std::chars_format::general;
        _precision = precision;
    }

    void set_range_separator(char separator) {
        _range_separator = separator;
    }

    template <class Matrix>
    void write_aligned(const Matrix& matrix) {
        using Row = internal::range_stored_value_t<const Matrix>;
        using Cell = internal::range_stored_value_t<const Row>;
        static_assert(internal::is_range_v<Row> && !internal::is_string_like_v<Row>,
                      "write_aligned requires a two-dimensional range");
        static_assert(!internal::is_range_v<Cell> || internal::is_string_like_v<Cell>,
                      "write_aligned requires scalar cells");
        write_aligned_matrix(matrix);
    }

    template <class Matrix>
    void println_aligned(const Matrix& matrix) {
        write_aligned(matrix);
        write_char('\n');
    }

    template <class... Args>
    void println(const Args&... args) {
        print(args...);
        write_char('\n');
    }

    template <class T>
    FastOutput& operator<<(const T& value) {
        write(value);
        return *this;
    }
};

}  // namespace utilities
}  // namespace m1une


#line 10 "verify/string/aho_corasick.test.cpp"
#include <tuple>
#line 12 "verify/string/aho_corasick.test.cpp"

namespace {

void check(
    const std::vector<std::string>& patterns,
    const std::string& text
) {
    m1une::string::AhoCorasick<4, 'a'> automaton;
    std::size_t total_length = 1;
    for (const std::string& pattern : patterns) {
        total_length += pattern.size();
    }
    automaton.reserve(total_length);
    for (int id = 0; id < int(patterns.size()); ++id) {
        assert(automaton.insert(patterns[id]) == id);
        assert(automaton.pattern_length(id) == int(patterns[id].size()));
    }
    automaton.build();
    assert(automaton.built());
    assert(automaton.pattern_count() == int(patterns.size()));
    assert(automaton.nodes().size() == automaton.node_count());
    assert(automaton.bfs_order().size() == automaton.node_count());
    assert(automaton.bfs_order().front() == automaton.root());

    std::vector<int> failure_parent_count(automaton.node_count(), 0);
    for (const auto& node : automaton.nodes()) {
        for (int child : node.failure_children) {
            failure_parent_count[child]++;
        }
    }
    for (int node = 1; node < int(automaton.node_count()); ++node) {
        assert(failure_parent_count[node] == 1);
        assert(
            automaton.node(automaton.node(node).failure).depth
            < automaton.node(node).depth
        );
        assert(
            std::find(
                automaton.node(automaton.node(node).parent).children.begin(),
                automaton.node(automaton.node(node).parent).children.end(),
                node
            ) != automaton.node(automaton.node(node).parent).children.end()
        );
        assert(
            automaton.node(automaton.node(node).parent)
                .next[automaton.node(node).parent_symbol]
            == node
        );
    }
    for (int id = 0; id < int(patterns.size()); ++id) {
        [[maybe_unused]] int terminal = automaton.pattern_node(id);
        assert(automaton.node(terminal).depth == int(patterns[id].size()));
        assert(
            std::find(
                automaton.node(terminal).pattern_ids.begin(),
                automaton.node(terminal).pattern_ids.end(),
                id
            ) != automaton.node(terminal).pattern_ids.end()
        );
    }

    std::vector<std::tuple<int, int>> actual;
    automaton.match(text, [&actual](int end, int pattern_id) {
        actual.emplace_back(end, pattern_id);
    });
    std::sort(actual.begin(), actual.end());

    std::vector<std::tuple<int, int>> expected;
    std::vector<long long> expected_count(patterns.size(), 0);
    for (int end = 0; end <= int(text.size()); ++end) {
        for (int id = 0; id < int(patterns.size()); ++id) {
            int length = int(patterns[id].size());
            if (
                length <= end &&
                text.compare(end - length, length, patterns[id]) == 0
            ) {
                expected.emplace_back(end, id);
                expected_count[id]++;
            }
        }
    }
    std::sort(expected.begin(), expected.end());
    assert(actual == expected);
    assert(automaton.count_occurrences(text) == expected_count);
}

void test_fixed() {
    check({}, "abacaba");
    check({""}, "");
    check({"", "", "a", "a", "aa", "ba"}, "aaaaba");

    m1une::string::AhoCorasick<10, '0'> digits;
    [[maybe_unused]] int first = digits.insert(std::string("12"));
    [[maybe_unused]] int second = digits.insert(std::string("2"));
    digits.build();
    auto count = digits.count_occurrences(std::string("1212"));
    assert(count[first] == 2);
    assert(count[second] == 2);

    digits.clear();
    assert(!digits.built());
    assert(digits.pattern_count() == 0);
    assert(digits.node_count() == 1);
}

void test_randomized() {
    std::uint64_t state = 313;
    auto random = [&state]() {
        state ^= state << 7;
        state ^= state >> 9;
        return state;
    };

    for (int trial = 0; trial < 4000; ++trial) {
        int pattern_count = int(random() % 15);
        std::vector<std::string> patterns;
        for (int id = 0; id < pattern_count; ++id) {
            int length = int(random() % 8);
            std::string pattern(length, 'a');
            for (char& symbol : pattern) {
                symbol = char('a' + random() % 4);
            }
            patterns.push_back(std::move(pattern));
        }

        int text_length = int(random() % 35);
        std::string text(text_length, 'a');
        for (char& symbol : text) {
            symbol = char('a' + random() % 4);
        }
        check(patterns, text);
    }
}

}  // namespace

int main() {
    m1une::utilities::FastInput fast_input;
    m1une::utilities::FastOutput fast_output;

    test_fixed();
    test_randomized();
    int n;
    fast_input >> n;
    m1une::string::AhoCorasick<> automaton;
    for (int i = 0; i < n; i++) {
        std::string pattern;
        fast_input >> pattern;
        automaton.insert(pattern);
    }
    automaton.build();

    int node_count = int(automaton.node_count());
    fast_output << node_count << '\n';
    for (int id = 1; id < node_count; id++) {
        const auto& node = automaton.node(id);
        fast_output << node.parent << ' ' << node.failure << '\n';
    }
    for (int i = 0; i < n; i++) {
        if (i) fast_output << ' ';
        fast_output << automaton.pattern_node(i);
    }
    fast_output << '\n';
}
Back to top page